DeepSeek opens the core capabilities of its app via API

Summary

DeepSeek announced that the capabilities behind its app are now available through the API. V4.1-Flash (deepseek-flash) handles web search, a deep-thinking search that reads pages during multi-step reasoning, file input for PDFs, Office files and images, automatic URL reading, and input/output safety checks on the server side, while OCR, speech recognition, and speech synthesis are offered as standalone APIs. Public-facing apps must enable safety checks, and developers remain responsible for content moderation. Extended capabilities incur tool usage fees on top of standard token charges. The publication date follows the date in the document URL (261113); the page itself shows no separate date.

Why it matters for our work

With search, file reading, and safety mechanisms bundled into the API, small teams can build agent apps quickly without reassembling these parts themselves. Tool usage fees are charged separately, so actual costs need checking.

Translated from the Korean original. Summaries may be translated and edited. Commentary reflects our perspective; forecasts remain the source’s views.